Information processing method, terminal equipment, server and storage medium

Abstract

The invention discloses an information processing method, terminal equipment, a server and a storage medium, and belongs to the field of computers. The method comprises the steps that a first interface comprising a question feedback window is displayed, and the question feedback window is used for providing an interaction entrance for multi-round dialogues for a user and a server so that the server can generate fault feedback information according to multi-round dialogue information; receiving fault feedback information sent by the server; determining a first fault scene corresponding to the fault feedback information and a scene fault tree corresponding to the first fault scene, wherein the scene fault tree comprises a plurality of fault nodes related to the first fault scene; performing fault detection on the plurality of fault nodes, and determining a solution according to a fault detection result; and displaying a second interface, wherein the second interface comprises related information of the solution. According to the embodiment of the invention, the fault fed back by the user can be accurately recognized through multiple rounds of dialogues, and the accuracy of fault detection and solution pushing is improved through detection based on the scene fault tree.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to an information processing method, terminal equipment, server, and storage medium. Background Art

[0002] With the rapid development of terminal and network technologies, terminal devices are becoming increasingly common in users' lives. However, problems are inevitable when using terminal devices. When a problem occurs, users can use the terminal device's intelligent detection function to diagnose the fault.

[0003] Currently, the intelligent detection function of terminal devices provides users with a variety of test items, such as system performance, communication and network, camera, screen, speaker, etc. When a terminal device encounters a problem, the user can select the test items related to the current device problem from a variety of test items and click the test button. The terminal device will then test the selected test items and recommend relevant solutions based on the test results.

[0004] However, the current classification of detection items is relatively coarse and depends on user selection. If the detection items selected by the user are inaccurate, the fault detection results will be inaccurate, and the pushed solutions will be inaccurate. Summary of the Invention

[0005] This application provides an information processing method, terminal device, server, and storage medium that improve the accuracy of fault detection and push solutions. The technical solution is as follows:

[0006] In a first aspect, an information processing method is provided, which is applied to a terminal device, and the method includes: displaying a first interface; the first interface includes a problem feedback window, which is used to provide an interactive entrance for a user and a server to conduct multiple rounds of dialogue, so that the server generates fault feedback information based on the multiple rounds of dialogue information, and the fault feedback information is used to indicate a fault scenario; receiving fault feedback information sent by the server; determining a first fault scenario corresponding to the fault feedback information and a scenario fault tree corresponding to the first fault scenario, the scenario fault tree including multiple fault nodes involved in the first fault scenario; performing fault detection on the multiple fault nodes respectively, and determining a solution based on the fault detection results; displaying a second interface, and the second interface including relevant information about the solution.

[0007] The problem feedback window is a fault feedback channel provided to users. This fault feedback channel acts as a bridge, establishing a communication connection between the user and the server. Users can conduct multiple rounds of dialogue with the server through this fault feedback channel to report more detailed and accurate problem descriptions to the server through multiple rounds of dialogue. Therefore, based on multiple rounds of dialogue, more accurate fault feedback information can be generated to accurately identify user faults and reduce the probability of inaccurate problem descriptions reported by users. Subsequently, by determining the scenario fault tree corresponding to the first fault scenario of the fault feedback information, the fault scenario corresponding to the user-reported usage problem and the various fault nodes involved in the fault scenario can be accurately located. By separately testing the multiple fault nodes in the located scenario fault tree, the accuracy and efficiency of fault detection are improved, and the efficiency of invalid detection is reduced. In addition, the accuracy of the solution determined based on this test result is also high. Based on this solution, the usage problems reported by users can be solved more targeted and effectively, improving the effectiveness of solving usage problems for users, thereby improving user satisfaction and user experience.

[0008] In one embodiment of the present application, before receiving the fault feedback information sent by the server, the first user input information in the problem feedback window is detected, and the first user input information is sent to the server; the question information sent by the server is received and displayed in the problem feedback window, and the question information is generated by the server after slot extraction of the first user input information, and the target slot of the slot extraction includes at least the fault type; the second user input information in the problem feedback window is detected, and the second user input information is sent to the server until the fault feedback information sent by the server is received, and the second user input information is the user's reply information based on the question information, and the multi-round dialogue information includes at least the first user input information, the second user input information and the question information.

[0009] In some embodiments, the target slot for slot extraction includes at least a fault type, so as to determine the fault type from the user's problem description. As an example, the fault type can be a fault type classified by a fault scenario, that is, the fault type can be a scenario type of a fault scenario, which is used to indicate the corresponding fault scenario. Of course, classification can also be performed in other ways, which is not limited in the embodiments of the present application. In addition, the target slot can also include one or more of the application identifier of the fault application, the time of fault occurrence, the probability of fault occurrence, and the problem summary, so as to determine the fault application, the time of fault occurrence, the probability of fault occurrence, or the problem summary from the user's fault description.

[0010] After performing slot extraction on the user input information, if the slot extraction result does not meet the requirements, for example, if the slot extraction result indicates that the slot information of at least some of the target slots has not been extracted, the server can generate a question based on the slot extraction result and display the question in a question feedback window. The question is used to instruct the user to provide the slot information of at least some of the slots, thereby guiding the user to provide undescribed problem information, thereby improving the detail and accuracy of the problem description. If the slot extraction result indicates that the slot information of all of the target slots has been extracted, there is no need to ask the user any further questions, and fault feedback information can be generated.

[0011] In this way, by asking precise questions, we can better reflect the user's actual problems, reduce ineffective conversations, improve conversation efficiency, and guide users to provide more detailed and accurate problem descriptions. Therefore, based on multiple rounds of conversations, more accurate fault feedback information can be generated to accurately identify user faults and reduce the probability of inaccurate problem descriptions in user feedback.

[0012] In one embodiment of the present application, the fault feedback information may indicate a fault scenario, such as scenario information of a first fault scenario occurring in a device, such as a scenario description, identifier, name, or code of the first fault scenario. Furthermore, the fault scenario may be characterized by at least one of the fault type, an application description of the fault application, the time of fault occurrence, the probability of fault occurrence, and a problem summary. Accordingly, the fault feedback information may include at least one of the fault type, an application description of the fault application, the time of fault occurrence, the probability of fault occurrence, and a problem summary. A problem summary refers to a summary of the problem description corresponding to multiple rounds of dialogue. For example, the fault feedback information may include fault information of a fault occurring in the first application.

[0013] In one embodiment of the present application, the fault scenario corresponding to the fault feedback information may be determined from multiple fault scenarios, and the fault scenario corresponding to the fault feedback information is the first fault scenario.

[0014] That is, multiple standardized fault scenarios are pre-set, and the terminal device can determine the fault scenario corresponding to the fault feedback information from the multiple fault scenarios, that is, the fault scenario that matches the fault feedback information, and use this fault scenario as the first fault scenario. In this way, the accuracy of determining the fault scenario can be improved.

[0015] In one embodiment of the present application, a scenario fault tree corresponding to the first fault scenario may be determined according to a mapping relationship between the fault scenarios and the scenario fault trees.

[0016] That is, a mapping relationship between fault scenarios and scenario fault trees is preconfigured. This mapping relationship includes a scenario fault tree corresponding to each of the multiple fault scenarios. The scenario fault tree corresponding to each fault scenario includes multiple fault nodes involved in each fault scenario, that is, multiple factors that may cause the fault scenario. After determining the first fault scenario corresponding to the fault feedback information, the scenario fault tree corresponding to the first fault scenario can also be determined based on the mapping relationship between the fault scenario and the scenario fault tree. In this way, the fault factors involved in the fault scenario can be accurately located, thereby facilitating subsequent accurate fault detection of the equipment, improving the accuracy and efficiency of fault detection, and reducing the probability of invalid detection.

[0017] In addition, each faulty node may also include at least one fault factor, that is, at least one factor that causes the faulty node to fail. Multiple faulty nodes may also be referred to as primary faulty nodes, and the fault factor of each faulty node may also be referred to as a secondary faulty node.

[0018] In one embodiment of the present application, fault detection is performed on multiple fault nodes separately, and the process of obtaining the fault detection result may include: using a parsing rule that matches the first fault node among multiple parsing rules to perform fault detection on the first fault node, and obtaining the detection result of the first fault node, the first fault node is any one of the multiple fault nodes, and the detection result is used to indicate whether the first fault node has a fault.

[0019] Among them, the multiple parsing rules include at least two of the following parsing rules: fault rules, command rules, node rules and code rules; fault rules refer to rules for parsing fault management data, command rules refer to rules for parsing databases, node rules refer to rules for parsing system files or configuration files, and code rules refer to rules for parsing by running preset algorithms.

[0020] By presetting multiple parsing rules for different fault nodes in the scenario fault tree, different parsing rules are used to parse different fault nodes to detect whether the corresponding fault nodes are faulty. This can improve the accuracy of fault detection.

[0021] In one embodiment of the present application, the first fault node may further include at least one fault factor that causes the first fault node to fail. The fault factor of the first fault node is the next-level fault node of the first fault node. For example, the first fault node may be referred to as a first-level fault node, and the fault factor may be referred to as a second-level fault node.

[0022] If the first fault node also includes at least one fault factor, the process of detecting the first fault node using a parsing rule that matches the first fault node among multiple parsing rules to obtain a detection result for the first fault node may further include: determining a parsing rule that matches each of the at least one fault factor from the multiple parsing rules, parsing each fault factor using the matching parsing rule, and obtaining a detection result corresponding to each fault factor. The detection result corresponding to each fault factor is used to indicate whether the corresponding fault factor has a fault. In this way, the detection result of each fault node includes the detection results of each fault factor of the fault node, which can further improve the accuracy of fault detection.

[0023] In one embodiment of the present application, a solution can be determined based on the fault detection results and service data. The service data can include one or more of existing service tickets, maintenance records, and a knowledge base. For example, the service data can be used to determine whether the fault detection result is a software or hardware issue, and a solution can be determined based on the fault detection result and the issue type. This can further improve the accuracy of the solution determination.

[0024] In one embodiment of the present application, the solution includes at least one of a handling suggestion, knowledge recommendations, guidance on branch maintenance methods, and fault repair execution methods. The handling suggestion includes repair suggestions or operational recommendations. The knowledge recommendations include explanations related to the fault, which can be accessed through the knowledge base. Guidance on branch maintenance methods may include information related to branch maintenance processes, such as mail-in repair methods or scheduled repair methods. Fault repair methods may include automatic repair methods or manual repair methods, which trigger the device to automatically repair the fault.

[0025] In one embodiment of the present application, the solution-related information includes one or more of a viewing suggestion control, a maintenance control, and an optimization control. If the solution-related information includes a viewing suggestion control, in response to a triggering operation on the viewing suggestion control, relevant knowledge about the fault corresponding to the fault feedback information or guidance information on the relevant knowledge is displayed; if the solution-related information includes a maintenance control, in response to a triggering operation on the maintenance control, guidance information on the branch maintenance process is displayed to guide the user to send in the repair or schedule a repair; if the solution-related information includes an optimization control, in response to a triggering operation on the optimization control, the fault corresponding to the fault feedback information is repaired.

[0026] By providing a variety of solution push methods, solutions can be adapted to different problem scenarios, thereby improving the universality of push solutions and user experience.

[0027] Secondly, an information processing method is proposed, which is applied to a server. The method includes: generating fault feedback information based on multi-round dialogue information in a problem feedback window of a terminal device; the problem feedback window is used to provide an interactive entrance for users and servers to conduct multi-round dialogues, and the fault feedback information is used for fault scenarios; and sending the fault feedback information to the terminal device.

[0028] The Problem Feedback Window provides users with a channel for reporting problems. This channel acts as a bridge, establishing a communication connection between the user and the server. Users can engage in multiple rounds of dialogue with the server through this channel, reporting more detailed and accurate problem descriptions. The server, based on these multiple rounds of dialogue with the user, can generate more accurate feedback information, precisely identifying the user's problem and reducing the likelihood of inaccurate problem descriptions in user feedback.

[0029] In one embodiment of the present application, the operation of generating fault feedback information based on multi-round dialogue information in the problem feedback window of the terminal device includes: receiving first user input information in the problem feedback window sent by the terminal device; performing slot extraction on the first user input information to obtain a slot extraction result, and the target slot extracted includes at least the fault type; when the slot extraction result indicates that the slot information of at least part of the target slots is not extracted, generating question information based on the slot extraction result, and the question information is used to instruct the user to provide slot information of at least part of the slots; sending the question information to the terminal device; continuing to receive second user input information in the problem feedback window sent by the terminal device until the slot information of all slots in the target slots is extracted based on the multi-round dialogue information with the user, and generating fault feedback information based on the multi-round dialogue information; wherein the second user input information indicates the user's reply information based on the question information, and the multi-round dialogue information includes at least the first user input information, the second user input information and the question information.

[0030] In some embodiments, the target slot for slot extraction includes at least a fault type to determine the fault type from the user's problem description. As an example, the fault type can be classified based on the fault scenario, and the fault type can be a scenario type of the fault scenario, which is used to indicate the corresponding fault scenario. Of course, classification can also be performed in other ways, and the embodiments of the present application are not limited to this. In addition, the target slot can also include one or more of the application identifier of the fault application, the time of fault occurrence, the probability of fault occurrence, and the problem summary to determine the fault application, the time of fault occurrence, the probability of fault occurrence, or the problem summary from the user's fault description.

[0031] After performing slot extraction on the user input information, if the slot extraction result does not meet the requirements, for example, if the slot extraction result indicates that the slot information of at least some of the target slots has not been extracted, the server can generate a question based on the slot extraction result and display the question in a question feedback window. The question is used to instruct the user to provide the slot information of at least some of the slots, thereby guiding the user to provide undescribed problem information, thereby improving the detail and accuracy of the problem description. If the slot extraction result indicates that the slot information of all of the target slots has been extracted, there is no need to ask the user any further questions, and fault feedback information can be generated.

[0032] In this way, by asking precise questions, we can better reflect the user's actual problems, reduce ineffective conversations, improve conversation efficiency, and guide users to provide more detailed and accurate problem descriptions. Therefore, based on multiple rounds of conversations, more accurate fault feedback information can be generated to accurately identify user faults and reduce the probability of inaccurate problem descriptions in user feedback.

[0033] In a third aspect, an information processing method is proposed, which is applied to an information processing system, wherein the information processing system includes a terminal device and a server, and the method includes: the terminal device displays a first interface; the first interface includes a problem feedback window, which is used to provide an interactive entrance for users and servers to conduct multiple rounds of dialogue; the server generates fault feedback information based on the multiple rounds of dialogue information in the problem feedback window of the terminal device, and the fault feedback information is used to indicate the fault scenario; the server sends the fault feedback information to the terminal device; the terminal device determines the first fault scenario corresponding to the fault feedback information and the scenario fault tree corresponding to the first fault scenario, and the scenario fault tree includes multiple fault nodes involved in the first fault scenario; fault detection is performed on the multiple fault nodes respectively, and a solution is determined based on the fault detection results; the terminal device displays a second interface, and the second interface includes relevant information about the solution.

[0034] In one embodiment of the present application, the method also includes: the terminal device detects the first user input information in the problem feedback window, and sends the first user input information to the server; the server performs slot extraction on the first user input information to obtain a slot extraction result, and the target slot extracted includes at least the fault type; when the slot extraction result indicates that the slot information of at least part of the target slots has not been extracted, the server generates question information based on the slot extraction result, and sends the question information to the terminal device, where the question information is used to instruct the user to provide slot information of at least part of the slots; the terminal device displays the question information in the problem feedback window, detects the second user input information in the problem feedback window, and sends the second user input information to the server until the server extracts the slot information of all slots in the target slot based on multiple rounds of dialogue information with the user, and generates fault feedback information based on the multiple rounds of dialogue information; wherein the second user input information indicates the user's reply information based on the question information, and the multiple rounds of dialogue information at least include the first user input information, the second user input information and the question information.

[0035] In a fourth aspect, a terminal device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method described in the first aspect when executed by the processor.

[0036] In a fifth aspect, a server is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method described in the second aspect when executed by the processor.

[0037] In a sixth aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, which, when executed on a computer, enables the computer to execute the method described in the first or second aspect above.

[0038] In a seventh aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the method described in the first or second aspect above.

[0039] The technical effect obtained by the fourth aspect is similar to the technical effect obtained by the corresponding technical means in the first aspect, and will not be repeated here.

[0040] The technical effect obtained in the fifth aspect is similar to the technical effect obtained by the corresponding technical means in the second aspect, and will not be repeated here.

[0041] The technical effects obtained in the above six aspects and the seventh aspect are similar to the technical effects obtained by the corresponding technical means in the above first aspect or the second aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a schematic diagram of the process of performing device detection through the intelligent detection function provided in an embodiment of the present application;

[0043] Figure 2 This is a schematic diagram of the process of performing device detection through the intelligent detection function provided in an embodiment of the present application;

[0044] Figure 3 This is a schematic diagram of a process for providing problem feedback through a self-feedback function provided in an embodiment of the present application;

[0045] Figure 4 This is a schematic diagram of a process for providing fault feedback through a problem feedback window provided in an embodiment of the present application;

[0046] Figure 5 This is a schematic diagram of push methods for several solutions provided in the embodiments of the present application;

[0047] Figure 6 is a schematic diagram of the user interface of several push solutions provided in the embodiments of the present application;

[0048] Figure 7 This is a schematic diagram of an interaction framework between a device side and a cloud side provided in an embodiment of the present application;

[0049] Figure 8 This is a schematic diagram of a multi-round conversation between a user and a robot provided by the example of this application;

[0050] Figure 9 This is a logic diagram of a fault detection module provided by the example of this application;

[0051] Figure 10 is a schematic diagram of a scenario fault tree for two fault scenarios provided in the examples of this application;

[0052] Figure 11 This is a flowchart of an information processing method provided by an embodiment of the present application;

[0053] Figure 12 This is a logical diagram for constructing a fault scenario tree provided by an embodiment of the present application;

[0054] Figure 13 This is a schematic diagram of a scenario fault tree for detecting a jamming or unsmooth failure scenario provided by the example of this application;

[0055] Figure 14 This is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application;

[0056] Figure 15This is a structural diagram of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0058] It should be understood that the “multiple” mentioned in this application refers to two or more. In the description of this application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in order to facilitate the clear description of the technical solution of this application, words such as “first” and “second” are used to distinguish between identical or similar items with basically the same functions and effects. Those skilled in the art can understand that words such as “first” and “second” do not limit the quantity and execution order, and words such as “first” and “second” do not necessarily limit them to be different.

[0059] It should also be understood that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0060] With the rapid development of terminal and network technologies, terminal devices are becoming increasingly prevalent in users' lives. However, during their use, users inevitably encounter some problems with these devices. To address these issues, current terminal devices provide users with self-service problem-solving capabilities, such as intelligent detection and self-feedback features.

[0061] Next, taking the intelligent detection function and self-feedback function as examples, the self-service problem-solving capabilities provided by current terminal devices are explained.

[0062] 1. Intelligent detection function.

[0063] The Smart Detection feature provides users with a variety of test items, including system performance, communications and networking, camera, screen, and speaker testing. When a device encounters a problem, the user can select the test item relevant to the issue from the various options provided and click the Detect button. In response to the user's actions, the device will then perform a test on the selected item and recommend solutions based on the results.

[0064] Please refer to Figure 1 and Figure 2 , Figure 1 and Figure 2 This is a schematic diagram of the process of performing device detection through the intelligent detection function provided by the embodiment of the present application. Figure 1 As shown in Figure (a), the user interface of the terminal device displays multiple application icons, such as the icons of the "Browser" application, the "Contacts" application, the "My Phone" application, the "Gallery" application, the "Call" application, and the "Message" application. The user can perform intelligent detection on the device through the "My Phone" application. For example, when a problem occurs in the use of the terminal device, the user can click the icon of the "My Phone" application. In response to the user's click operation, the terminal device displays the following Figure 1 The user interface shown in Figure (b) includes multiple controls, such as a device detection control for providing intelligent detection functions, a store appointment control for providing store appointment services, a charging standard control for providing charging standard viewing services, and a mail-in repair service control for providing mail-in repair services. The user can click on the device detection control, and in response to the user's click operation, the terminal device displays the following Figure 1 The user interface shown in Figure (c) includes a permission acquisition pop-up window. The permission acquisition pop-up window displays permission acquisition information to prompt the user which permissions the smart detection function needs to obtain from the terminal device when using the smart detection function, such as location information permission, Bluetooth permission, camera permission, microphone permission, storage permission, address book permission, application list permission, etc. In addition, the permission acquisition pop-up window also includes a "Cancel" option and an "Agree" option. If the user clicks the "Agree" option, the terminal device displays the following in response to the user's operation: Figure 1The user interface shown in Figure (d) includes multiple detection items, such as "system performance", "application message reception delay", "communication network", "wireless local area network (WLAN)", "Bluetooth", "gravity sensing", "charging and battery", and "real-time charging" detection items. In addition, the user interface may also include an "all" option and a "detect now" option. The "all" option is used to indicate all the above-mentioned detection items, and the "detect now" option is used to trigger detection. Users can select detection items related to the usage problems of the current device from a variety of detection items according to their own judgment, and then click the "detect now" option. Generally speaking, in order to avoid missing detection content, most users will select the "all" option.

[0065] For example, suppose the user selects the "All" option. In response to the user's selection, refer to Figure 2 In Figure (a), all options and all test items are switched to the selected state. After selecting the "All" option, the user can click the "Test Now" option. In response to the user's operation, the terminal device will start to test all test items such as system performance, application message reception delay, communication network, WLAN, Bluetooth, gravity sensor, charging and battery, and real-time charging and battery, and display the following information: Figure 2 The user interface shown in Figure (b) in the figure displays the progress information of the test such as the test progress bar. After all the test items are tested, the terminal device displays the following Figure 2 The user interface shown in Figure (c) includes a "re-test" option and a "view suggestions" option. If the user clicks the "view suggestions" option, the terminal device displays the following in response to the user's operation: Figure 1 The user interface shown in FIG. 5(d) includes a description of the detection result and related processing suggestions. In addition, if the user clicks the "re-detect" option, the terminal device can also re-detect in response to the user's operation.

[0066] According to the above Figure 1 and Figure 2It can be seen that the classification of the detection items provided by the intelligent detection function of the terminal device is relatively coarse, and is classified based on large functional categories such as the terminal device system, network, and various functional components. Therefore, these detection items may not accurately match the device problem. Moreover, the detection items of the intelligent detection function rely on user selection. If the detection items selected by the user are inaccurate, for example, the detection items selected by the user are irrelevant to the device problem or there is a deviation, it will lead to inaccurate problem detection results, and then the solution determined based on the problem detection results will also be inaccurate. The device problem may not be solved according to the determined solution. Therefore, the effect of solving the device problem for the user is poor, and user satisfaction is low. In addition, when performing intelligent detection, if the user selects the "all" option, that is, selects full detection, there will be more detection items, the detection time will be longer, and the results will be mixed, with more interference information, and the accuracy of fault detection will be low.

[0067] 2. Self-feedback function.

[0068] The self-feedback function can provide users with a problem feedback portal. Users can provide problem feedback through the problem feedback portal so that online customer service can recommend knowledge based on the user's feedback. For example, based on the user's feedback, the customer service can guide the user to view instructions and operation suggestions related to the device problem.

[0069] Please refer to Figure 3 , Figure 3 This is a schematic diagram of a process of providing problem feedback through the self-feedback function provided by an embodiment of the present application. Figure 1 As shown in the user interface of Figure (c), after the user clicks the "Agree" option, the terminal device can display the following Figure 3 The user interface shown in Figure (a) is as follows. Figure 3 As shown in Figure (a), the user interface includes multiple detection items, such as "system performance", "application message reception delay", "communication network", "WLAN", "Bluetooth", "gravity sensing", "charging and battery", and "real-time charging", and may also include an "all" option. In addition, the user interface also includes more controls (the three dots in the upper right corner of the user interface in the figure). If the user clicks on more controls, in response to the user's operation, Figure 3 As shown in Figure (b) of the figure, the user interface pops up a pop-up window including options such as diagnosis analysis, remote service, problem feedback and about. If the user clicks the problem feedback option, the terminal device will display the following in response to the user's operation: Figure 3The problem feedback window shown in Figure (c) is a window for users to interact with online customer service. Online customer service can be manual customer service or artificial intelligence (AI) customer service. Users can enter a one-sentence description of the problem in the problem feedback window, such as "WeChat freezes". After the user enters the problem description, the online customer service can recommend knowledge based on the problem description entered by the user. Figure 2 As shown in Figure (d), after the user enters "WeChat lags" in the problem feedback window, the online customer service can search the knowledge base for relevant knowledge such as problem descriptions and action suggestions that match "WeChat lags" and provide the found knowledge to the user through the problem feedback window for the user to review. Among them, the problem description matching "WeChat lags" can be "WeChat lags may be caused by memory or network issues", and the action suggestion can be "Please try the following method: Please clear the cache first. Step 1.1.1, enter the mobile manager, step 1.1.2, click Clear cache, etc."

[0070] According to the above Figure 3 As can be seen, the self-feedback feature only supports knowledge recommendations, which may not be able to effectively solve device problems for users. Furthermore, the self-feedback feature currently recommends knowledge based solely on a single sentence of the problem description entered by the user, resulting in a low degree of match between the recommended knowledge and the reported problem. Furthermore, the knowledge base is currently manually curated, so the amount and content of recommended knowledge are limited. This results in poor problem-solving effectiveness and low user satisfaction.

[0071] In response to the above problems, an embodiment of the present application provides an information processing method, which is applied to an interactive system including a terminal device and a server, where the terminal device and the server can be connected via a wired network or a wireless network.

[0072] Among them, terminal devices include but are not limited to mobile phones, mobile phones, foldable phones, smart terminals, laptops, smart wearable devices, tablets, desktops, portable computers, handheld computers, wireless terminal devices, vehicle-mounted devices, smart home devices, communication equipment, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (portable android devices, PADs), portable multimedia players (PMPs), etc. The embodiments of the present application do not limit the specific type of the terminal device. The server is a background server that provides information processing services for the terminal device, and can be a computer or a computer cluster, etc. The terminal device is also called the end side, and the server is also called the cloud side.

[0073] In this method, the terminal device can display a problem feedback window, which provides an interactive entry point for a multi-round dialogue between the user and the server. Based on the multi-round dialogue information in the problem feedback window, fault feedback information representing a fault scenario can be generated. Based on this fault feedback information, the terminal device can determine a first fault scenario corresponding to the fault feedback information and a scenario fault tree for the first fault scenario, which includes multiple fault nodes involved in the first fault scenario. The terminal device then performs tests on each of these multiple fault nodes, determines solutions based on the test results, and displays relevant information about the solutions to the user.

[0074] The problem feedback window is a fault feedback channel provided to users. This fault feedback channel acts as a bridge, establishing a communication connection between the user and the server. Users can conduct multiple rounds of dialogue with the server through this fault feedback channel to report more detailed and accurate problem descriptions to the server through multiple rounds of dialogue. Therefore, based on multiple rounds of dialogue, more accurate fault feedback information can be generated to accurately identify user faults and reduce the probability of inaccurate problem descriptions reported by users. Subsequently, by determining the scenario fault tree corresponding to the first fault scenario of the fault feedback information, the fault scenario corresponding to the user-reported usage problem and the various fault nodes involved in the fault scenario can be accurately located. By separately testing the multiple fault nodes in the located scenario fault tree, the accuracy and efficiency of fault detection are improved, and the efficiency of invalid detection is reduced. In addition, the accuracy of the solution determined based on this test result is also high. Based on this solution, the usage problems reported by users can be solved more targeted and effectively, improving the effectiveness of solving usage problems for users, thereby improving user satisfaction and user experience.

[0075] In the embodiment of the present application, the server can generate fault feedback information based on the multi-round dialogue information in the problem feedback window, or the terminal device can generate fault feedback information based on the multi-round dialogue information in the problem feedback window. This embodiment of the present application is not limited to this. For ease of explanation, the following example uses the server generating fault feedback information based on the multi-round dialogue information in the problem feedback window and sending the fault feedback information to the terminal device.

[0076] In one embodiment, the server can generate questions based on the problem description entered by the user in the problem feedback window, and guide the user to enter a more detailed and accurate problem description, thereby realizing multiple rounds of dialogue between the user and the server until the server can generate fault feedback information based on the multi-round dialogue information.

[0077] Please refer to Figure 4 , Figure 4 This is a schematic diagram of a process for providing fault feedback through a problem feedback window provided by an embodiment of the present application. Figure 3The user interface shown in Figure (a) in FIG, after the user clicks the more controls in the upper right corner of the user interface, can display the following Figure 4 The user interface shown in Figure (a) in FIG. 1 includes options such as diagnostic analysis, remote service, problem feedback, and about in the upper right corner. If the user clicks the problem feedback option, the following information may be displayed in response to the user's operation: Figure 4 The problem feedback window shown in Figure (b) is where users can provide feedback. For example, please refer to Figure 4 In Figure (b), after the user enters the problem description "phone freezes" in the problem feedback window, the intelligent customer service (server) can generate a question message "I am very sorry to give you a bad experience. I will work with you to solve it. Which scenario did the freeze occur?" and provide a variety of freeze scenario options for users to choose from, such as freeze when playing games, freeze after system upgrades, freeze in chat applications, freeze in applications (APP), freeze when playing videos, freeze when taking photos and videos, freeze in daily operations, and other freeze scenarios. If the user clicks on the APP freeze, in response to the user's operation, such as Figure 4 As shown in Figure (c) in the question feedback window, multiple application options can be provided for the user to choose. Assuming that the user selects application A, please refer to Figure 4 In Figure (d), the intelligent customer service representative can continue to ask, "Does this problem occur frequently?" The user can then respond with, "Often." This allows for multiple rounds of dialogue between the user and the server, guiding the user to enter a more detailed and accurate description of the problem.

[0078] It should be noted that Figure 4 The explanation is only given by taking the example of entering the problem feedback window through the currently existing problem feedback entrance, that is, entering the smart detection page through the device detection control of the "My Phone" application, and entering the problem feedback window through the problem feedback option triggered by more controls on the smart detection page. It should be understood that other entrances can also be configured for the problem feedback window provided in the embodiment of the present application, and the problem feedback window can be entered through other entrances. The embodiment of the present application does not limit this.

[0079] After the user has conducted multiple rounds of dialogues with the server through the problem feedback window, the terminal device can automatically perform fault detection based on the fault feedback information generated by the multiple rounds of dialogues, without the user having to manually select the detection items. For example, the terminal device can determine the fault scenario corresponding to the fault feedback information and the scenario fault tree of the fault scenario, and detect multiple fault nodes in the scenario fault tree separately, and then recommend solutions to the user based on the fault detection results.

[0080] In one embodiment, the solution may include one or more of: handling suggestions, knowledge recommendations, guidance on branch maintenance methods, and fault repair execution methods. Handling suggestions include repair suggestions or operational recommendations. Knowledge recommendations include explanations related to the fault, which can be accessed through the knowledge base. Guidance on branch maintenance methods may include information about branch maintenance processes, such as mail-in repair methods or scheduled repair methods. Fault repair methods may include automatic repair methods or manual repair methods, which trigger the device to automatically repair the fault.

[0081] As an example, the terminal device can determine a solution based on the detection results and display relevant information about the solution. Among them, the relevant information of the solution may include a description of the fault, and may also include one or more of processing suggestions, viewing suggestion controls, maintenance controls, and optimization controls. The viewing suggestion control is used to trigger relevant knowledge about the device fault, such as triggering the display of relevant knowledge about the fault corresponding to the fault feedback information or guiding information for viewing relevant knowledge, and the guiding information is used to guide the user to view the relevant knowledge. The maintenance control (such as the "Guide Maintenance" control or the "I Want Repair" control, etc.) is used to trigger the guidance information of the branch maintenance process to guide the user to send in for repair or make an appointment for repair. The optimization control (such as the "One-click Optimization" control or the "Optimize Now" control) is used to trigger the device to automatically repair the fault, such as repairing the fault corresponding to the fault feedback information.

[0082] Please refer to Figure 5 , Figure 5 This is a schematic diagram of the push methods of several solutions provided in the embodiments of this application. Figure 5 As shown, the push methods of solutions can include prompt information, knowledge base viewing, guided maintenance, and automatic (or manual) repair. Among them, prompt information refers to the display of fault descriptions and handling suggestions on the end side. Knowledge base viewing refers to the display of the "View Suggestions" control on the end side, through which users view the guidance information or instructions of the knowledge base. Guided maintenance refers to the display of the "I want repair" button on the end side, through which users view the guidance information of the branch maintenance process to perform operations such as sending in repairs or making an appointment for repairs. Automatic repair refers to the display of the "One-click optimization" or "Immediate optimization" control on the end side, through which users can trigger the device to perform automatic repairs.

[0083] Please refer to Figure 6 , Figure 6 Schematic diagram of the user interface of several push solutions provided by the embodiment of this application. Figure 6 The push interface of the solution shown in Figure (a) includes a description of the fault and handling suggestions. Figure 6The push interface of the solution shown in Figure (b) includes fault description, handling suggestions and a "View Suggestions" control. Users can click the "View Suggestions" control to view relevant knowledge about the current device fault in the knowledge base. Figure 6 The push interface of the solution shown in Figure (c) includes fault description, handling suggestions and "I want repair" control. Users can click the "I want repair" control to send in the repair or make an appointment for repair. Figure 6 The push interface of the solution shown in Figure (d) includes a fault description, handling suggestions, and a "one-click optimization" control. Users can trigger the device to automatically repair by clicking the "one-click optimization" control.

[0084] It should be understood that Figure 5 and Figure 6 The push methods of the above-mentioned solutions are merely used as examples for illustration. In other implementations, other methods may also be used to push solutions, and the embodiments of the present application do not limit this.

[0085] Next, the software framework of the interactive system involved in the embodiment of the present application is illustrated.

[0086] Please refer to Figure 7 , Figure 7 This is a schematic diagram of an interaction framework between the terminal side and the cloud side provided in an embodiment of the present application. Figure 7 As shown, the terminal device on the end side may include an intelligent detection application, which may provide a front-end robot chat framework (such as a question feedback window) and may also include an intelligent detection module. The server on the cloud side includes a robot engine.

[0087] The front-end robot chat framework provides an interactive entry point for users to engage in multi-round conversations with robots (also known as online customer service or intelligent customer service). For example, the front-end robot chat framework can detect user operations and receive user input information. The terminal device can then feed the user input information received through the front-end robot chat framework back to the robot engine on the cloud side.

[0088] The robot engine can communicate with the intelligent detection application in real time. The robot engine includes an intent recognition module, a slot extraction module, an intelligent question-and-answer module, and a task decision module. It may also include a knowledge recommendation module. The slot extraction module extracts slots from user input received through the front-end robot chat framework, generating slot extraction results. The intelligent question-and-answer module generates questions based on the slot extraction results and pushes them to the front-end robot chat framework on the client side for display. The intent recognition module identifies intents from multiple rounds of conversations to obtain conversation intents. Conversation intents can be problems or knowledge queries. The task decision module assigns tasks based on conversation intents. For example, if the conversation intent is a problem, fault feedback information is generated based on the multiple rounds of conversations and sent to the intelligent detection module on the client side for intelligent detection. If the conversation intent is a knowledge query, knowledge recommendation content is generated and pushed to the front-end robot chat framework for display.

[0089] As an example, the target slot for slot extraction by the slot extraction module may include a fault type, and may also include one or more of an application identifier of the faulty application, a fault occurrence time, a fault occurrence probability, and a problem summary.

[0090] Next, we will use the example of multiple target slots including fault type, fault application, and fault occurrence time to explain. Figure 8 , Figure 8 This is a schematic diagram of a multi-round conversation between a user and a robot provided by the example of this application. Figure 8As shown, the first round of the conversation process involves the user inputting "My phone is lags." The robot engine parses the user input and identifies the problem scenario as: fault, phone lag. The robot engine extracts the slots for the user input "My phone is lags" based on the fault type, faulty application, and fault occurrence time. Slot extraction result 1: The lag scenario for the fault type slot requires a scenario, meaning the fault type of phone lag is extracted, but the specific lag scenario is not; the fault application requires clarification, meaning the slot information for the fault application slot is not extracted; and the fault occurrence time requires clarification, meaning the slot information for the fault occurrence time slot is not extracted. Based on the slot extraction results, the robot engine generates a question, "In what scenarios and when did the lag occur?" to guide the user to provide the missing slot information. The second round of the conversation process involves the user inputting, "App A's live streaming often lags," based on the question information. The robot engine extracts slot information for the user input "App A live stream frequently freezes" based on the slots for which no slot information was extracted. Slot extraction result 2 is obtained: the fault type slot information is "App A short video - App A function abnormality - App A freezes," the fault application slot information is "App A," and the occurrence time slot information is "Yesterday's time point 1 / time point 2 / time point 3." Additionally, the target slot can include a problem summary. The problem summary slot information is: "App A frequently freezes."

[0091] The intelligent detection module includes a fault detection module and a solution recommendation module, and may also include a user evaluation module. The fault detection module is used to perform intelligent detection based on the fault feedback information sent by the robot engine. The solution recommendation module is used to determine the solution based on the fault detection results of the fault detection module and push the solution to the user, such as pushing the solution to the front-end robot chat framework and displaying it to the user through the front-end robot chat framework. The user evaluation module is used to obtain the user's evaluation of the solution recommended by the solution recommendation module. For example, the user evaluation module can trigger the terminal device to display an evaluation interface, which is used to instruct the user to evaluate the solution recommended by the solution recommendation module, and then detect the user's input operation to obtain the user's evaluation.

[0092] As an example, see Figure 9 , Figure 9 This is a logic diagram of a fault detection module provided by this application example. Figure 9As shown, the fault detection module includes a scenario conversion model and a diagnosis engine. The scenario conversion model is used to convert the fault feedback information into the corresponding fault scenario. For example, the fault scenario module pre-stores a variety of fault scenarios, and these multiple fault scenarios can be pre-configured standardized fault scenarios. The scenario conversion model can determine the fault scenario that matches any fault feedback information from the multiple fault scenarios to convert different fault feedback information into the corresponding fault scenario. The diagnosis engine is used to perform fault diagnosis on the terminal device according to the scenario fault tree of the fault scenario. For example, according to the diagnosis strategy of each node in the scenario fault tree of the fault scenario, the scenario fault tree of the fault scenario is subjected to fault detection (also called fault diagnosis) to obtain a fault detection result (also called fault diagnosis result). The fault detection result can indicate a device fault, that is, a fault that occurs in the device. The diagnosis engine can send the fault detection result to the solution recommendation module so that the solution recommendation module determines and pushes a solution based on the fault detection result.

[0093] As an example, each of the aforementioned multiple fault scenarios is configured with a corresponding scenario fault tree. The scenario fault tree corresponding to each fault scenario includes multiple fault nodes involved in the corresponding fault scenario, i.e., multiple factors that lead to the occurrence of the corresponding fault scenario. Furthermore, each fault node may also include at least one fault factor, i.e., at least one factor that causes the fault node to fail. The multiple fault nodes may also be referred to as primary fault nodes, and the fault factor of each fault node may also be referred to as a secondary fault node.

[0094] Please refer to Figure 10 , Figure 10 This is a schematic diagram of the scenario fault tree for two fault scenarios provided in the example of this application. Figure 10The figure shows the scenario fault trees for two fault scenarios: "short video app live streaming freezes" and "instant messaging app video call freezes." The fault tree for the "short video app live streaming freezes" scenario includes the following fault nodes: settings-related, slow data service access, transmission protocol (TP) failure, central processing unit (CPU) failure, malicious keepalive, memory leak, and Wi-Fi access anomalies. The fault tree for the "WeChat video call freezes" scenario includes the following fault nodes: slow data service access, malicious keepalive, memory leak, Wi-Fi access anomalies, WeChat application diagnosis, slow camera, and service freezes. Settings-related fault factors include low power mode, frame rate, and game acceleration. Data service slowness fault factors include resource preemption conflicts, slow game server response, and network issues. TP fault factors include touchscreen ghosting and touchscreen wake-up failure. CPU load fault factors include high CPU load and temperature control frequency limiting. Malicious keepalive fault factors include risky applications. Memory leaks include application memory leaks. WiFi internet anomalies include frequent disconnections and slow internet speeds. WeChat application diagnostics include excessive WeChat database size and version detection. Camera slowness includes underlying algorithm anomalies. Service freezes include abnormal service freezes.

[0095] It should be understood that Figure 10 Only two fault scenarios, "TikTok live broadcast freeze" and "WeChat video call freeze", are used as examples for illustration. The above-mentioned multiple fault scenarios may also include other fault scenarios. The scenario fault tree of each fault scenario may also be in other forms, such as including other fault nodes. The specific fault scenario and the scenario fault tree of the fault scenario can be configured according to actual needs. The embodiments of the present application do not limit the specific content of the fault scenario and the scenario fault tree.

[0096] Next, the information processing method provided in the embodiments of the present application is introduced in detail.

[0097] Please refer to Figure 11 , Figure 11 This is a flow chart of an information processing method provided by an embodiment of the present application. This embodiment of the present application takes the intelligent detection application of the terminal device to provide a problem feedback window for the user as an example. Figure 11 As shown, the method includes the following steps:

[0098] S11. The user triggers a problem feedback window of the intelligent detection application.

[0099] The Problem Feedback window provides an interactive entry point for users and the server to engage in multi-round dialogue. For example, a user can use the Problem Feedback window to enter a description of a device problem, enabling a multi-round dialogue with the robot engine. Device problems can include malfunctions, usage issues, and other issues, which are not limited in this embodiment.

[0100] In one embodiment, the problem feedback window may be provided by a smart detection application on the terminal device. The user may first launch the smart detection application on the terminal device, and then trigger the problem feedback window in the application interface of the smart detection application. For example, the operation of triggering the problem feedback window may be clicking a problem feedback option in the application interface of the smart detection application.

[0101] It should be understood that the embodiment of the present application is only explained by taking the example of opening the problem feedback window through the intelligent detection application. In other embodiments, the problem feedback window can also be opened by other means, and the embodiment of the present application does not limit this.

[0102] S12. In response to a triggering operation by the user, the terminal device displays a first interface, which includes a question feedback window.

[0103] For example, the intelligent detection application of the terminal device displays a first interface including a problem feedback window.

[0104] As an example, the smart detection application is integrated into the "My Phone" application. The process of the user triggering the problem feedback window of the smart detection application can be as follows: Figure 1 and Figure 4 As shown. Figure 1 As shown, the user first clicks the icon of the "My Phone" application, and then clicks the device detection control to start the device detection application. After that, click the more controls in the upper right corner of the smart detection application interface to trigger the terminal device to display the following Figure 4 The user interface shown in Figure (a) includes a question feedback option. Figure 4 As shown in Figure (a), the user can click on the question feedback option, and in response to the user's operation, the following Figure 4 FIG. 8 (b) shows a user interface including a problem feedback window, in which a user may enter a problem description (eg, a fault description).

[0105] S13. The user enters first user input information in the problem feedback window.

[0106] In one embodiment, the problem feedback window includes an editing entry through which the user can edit and enter the first user input information. For example, the user can use text or voice to describe the device problem encountered in the editing entry of the problem feedback window.

[0107] The editing entry can be an input box, etc. For example, please refer to Figure 4 In Figure (b), the problem feedback window includes an input box at the bottom of the window. When the phone freezes, the user can enter "phone freezes" in the input box at the bottom (corresponding to the first user input information).

[0108] S14. The terminal device detects the first user input information in the problem feedback window.

[0109] S15. The terminal device sends the first user input information to the server.

[0110] The intelligent detection application of the terminal device detects the first user input information in the problem feedback window and sends the first user input information to the robot engine of the server.

[0111] S16. The server performs slot extraction on the first user input information to obtain a slot extraction result. If the slot extraction result does not meet the requirements, the server generates question information according to the slot extraction result.

[0112] In an embodiment of the present application, the robot engine in the server may include a large language model and employ machine learning algorithms based on artificial intelligence (AI) to implement natural language processing (NLP), such as word segmentation, classification, and keyword matching. The robot engine may perform slot extraction on the first user input information to obtain a slot extraction result. Furthermore, the robot engine may generate question information based on the slot extraction result to guide the user to continue entering a more detailed and accurate question description.

[0113] In some embodiments, the target slot for slot extraction includes at least a fault type, thereby determining the fault type from the user's problem description. As an example, the fault type can be categorized by fault scenario, where the fault type can be a category of fault scenario, indicating the corresponding fault scenario. Of course, other categorization methods are also possible, and this embodiment of the present application is not limited thereto.

[0114] In addition, the target slot may also include one or more of the application identifier of the faulty application, the time of fault occurrence, the probability of fault occurrence, and the problem summary, so as to determine the faulty application, the time of fault occurrence, the probability of fault occurrence, or the problem summary from the user's fault description.

[0115] It should be understood that the target slot can be set according to actual needs and can also include other slots, which is not limited in the embodiments of the present application.

[0116] Furthermore, if the slot extraction result does not meet the requirements, for example, if the slot extraction result indicates that the slot information of at least some of the target slots has not been extracted, the robot engine can also generate a question based on the slot extraction result. This question is used to instruct the user to provide the slot information of at least some of the target slots, thereby guiding the user to provide the undescribed problem information, thereby improving the detail and accuracy of the problem description.

[0117] For example, see Figure 4 In Figure (b), the target slot includes the fault type, faulty application, and fault occurrence time. After the user enters the fault description "phone freezes" in the problem feedback window, the intelligent customer service (robot engine) can extract the slot for "phone freezes" and then generate a question based on the slot extraction result, "I'm very sorry for the bad experience. I will work with you to solve it. In which scenario did the freeze occur?" to guide the user to describe the fault scenario in detail.

[0118] In one embodiment, the robot engine can further generate multiple candidate scenarios based on the first user input information to prompt and guide the user's next round of responses. In this way, the question information includes not only the above question, but also multiple candidate scenarios. Figure 4 Multiple candidate scenarios are shown in Figure (b): lag in playing games, lag after system upgrade, lag in chat applications, lag in APP, lag in playing videos, lag in taking photos and videos, lag in daily operations, and other lag scenarios.

[0119] Typically, natural language processing involves numerous algorithms and databases, requiring significant memory and computing power. Therefore, the robot engine can be deployed on the cloud to reduce power consumption on the client side and improve conversation efficiency. It should be understood that in other embodiments, the robot engine can also be deployed on the client side, with the terminal device performing slot extraction on the user input and generating question information based on the slot extraction results.

[0120] In the embodiment of the present application, slot extraction is to extract information related to a specified slot from a specified text (i.e., user input information). The target slot of the slot extraction is related to the scenario corresponding to the problem description input by the user. The target slot indicates the keywords required to generate fault feedback information, such as fault type, fault application, fault occurrence time or fault occurrence probability. Slot extraction can be achieved by the robot engine performing NLP algorithm processing on the first user input information. There can be one or more target slots for each scenario.

[0121] If the slot extraction result indicates that slot information for all target slots has been extracted, there is no need to ask the user any further questions; fault feedback information can be generated. If the slot extraction result indicates that slot information for at least some of the target slots has not been extracted, that is, slot information for all of the target slots has not been extracted, or slot information for some of the target slots has not been extracted, the user is required to provide the information. A question is generated based on the slot extraction result. The question can be generated based on some of the slots, guiding the user to provide the slot information for at least some of the slots.

[0122] It should be noted that in one implementation, if after a preset number of rounds (e.g., 5 or 6 rounds), the slot information for all target slots is not obtained, that is, the slot information for only some of the target slots is obtained, then the slot information for the currently extracted slots and the user input information is supplemented, and fault feedback information is generated to improve dialogue efficiency. In another implementation, if the user fails to respond to the slot information for some slots within a preset number of times (e.g., 2 or 3 times), the robot engine can change the question structure, or supplement the slot information based on the currently extracted slot information and the user input information, to reduce invalid dialogue and improve dialogue efficiency.

[0123] In this embodiment, the server's robot engine extracts slot information from each round of user input. If the slot extraction fails to find the slot information for certain slots, it generates questions to guide the user to provide slot information for certain slots, until the slot information for all target slots is extracted based on multiple rounds of conversation information. Compared to solutions that rely solely on the user to describe the problem or require the user to select the fault type, using precise questions can better reflect the user's actual problem, reduce ineffective conversations, and improve conversation efficiency.

[0124] S17. The server sends a question message to the terminal device.

[0125] S18. The terminal device displays the question information in the question feedback window.

[0126] The robot engine of the server sends the generated question information to the intelligent detection application of the terminal device, and the intelligent detection application displays it in the question feedback window.

[0127] In the embodiment of the present application, the question feedback window is equivalent to a bridge, establishing a communication connection between the terminal device and the robot engine. The question feedback window sends the user's question description to the robot engine, and the robot engine sends the question information to the question feedback window.

[0128] In some scenarios, the question information includes a question and multiple candidate scenarios. In this case, the smart detection application displays the question and multiple candidate scenario options in the question feedback window. The user can directly select any one or more of the above candidate scenarios. At the same time, the smart detection application provides an editing entrance in the question feedback window, such as Figure 4 In the input box shown in Figure (b), "Please enter your question." Users can also ignore the above candidate scenarios and use text or voice to describe the problem again in the editing entrance, that is, enter the problem description.

[0129] S19. The user enters second input information in the problem feedback window.

[0130] The second user input information may be a reply information of the user based on the question information. That is, the user can reply based on the question information displayed in the question feedback window, and the reply information may be self-edited or may be a selected candidate scenario.

[0131] S20. The terminal device detects second user input information in the problem feedback window.

[0132] S21. The terminal device sends second user input information to the server.

[0133] The intelligent detection application of the terminal device detects the second user input information in the problem feedback window and sends the second user input information to the robot engine of the server.

[0134] S22. The server performs slot extraction on the second user input information to obtain a slot extraction result.

[0135] The robot engine may continue to perform slot extraction on the second user input information to obtain a slot extraction result, and determine whether slot information of all slots in the target slots has been extracted according to the slot extraction result.

[0136] S23. When the slot extraction result meets the requirements, the server generates fault feedback information based on multiple rounds of dialogue.

[0137] When the slot extraction result meets the requirements, for example, when the slot information of all the target slots is determined to be extracted according to the slot extraction result, the robot engine can generate fault feedback information based on the multi-round dialogue information.

[0138] The multi-round dialogue information includes at least the first user input information, the second user input information, and the question information. The fault feedback information is used to indicate the fault scenario. The fault feedback information can indicate the fault scenario. For example, the fault feedback information can include scenario information of the first fault scenario that occurred on the device. For example, the fault feedback information includes the scenario description, identifier, name, or code of the first fault scenario. For another example, the fault scenario can be characterized by at least one of the fault type, application description of the faulty application, fault occurrence time, fault occurrence probability, and problem summary. The fault feedback information can include at least one of the fault type, application description of the faulty application, fault occurrence time, fault occurrence probability, and problem summary. The problem summary refers to the summary of the problem description corresponding to the multi-round dialogue. For example, the fault feedback information can include fault information of the fault that occurred on the first application.

[0139] As an example, the robot engine can generate fault feedback information fault scenarios based on slot extraction results corresponding to multi-round dialogue information, such as generating fault feedback information based on slot extraction results of multi-round user input information in multi-round dialogue information.

[0140] Furthermore, if the slot extraction results do not meet the requirements, for example, if the slot extraction results determine that slot information for all target slots has not yet been extracted, the robot engine can continue to generate question information based on the slot extraction results and send the question information to the terminal device, which will then display the question information in a question feedback window, thereby guiding the user to continue responding based on the question information until slot information for all target slots has been extracted, at which point the questioning process stops. In other words, if the slot extraction results do not meet the requirements, the next round of conversation can continue until slot information for all target slots has been extracted.

[0141] As an example, if the target slot includes the fault type, the fault feedback information may include the phone freezing. If the target slot includes the faulty application and fault type, the fault feedback information may include Application A freezing. If the target slot includes the faulty application, fault type, and fault frequency, the fault feedback information may include Application A frequently freezing.

[0142] The embodiment of the present application does not limit the specific form of the target slot and fault feedback information, and can be applied to more application scenarios, thereby improving the universality of the solution.

[0143] In some embodiments, during a multi-round dialogue process, dialogue intentions are identified on the multi-round dialogue information to obtain dialogue intentions, where the dialogue intentions are failure problems or knowledge inquiries. When the dialogue intentions are failure problems, fault feedback information is generated.

[0144] In the embodiment of the present application, intent recognition runs through the entire conversation process, and intent recognition may include slot extraction, generation of question information, and conversation intent recognition. Among them, slot extraction and generation of question information are used to assist in the recognition of conversation intent. During multiple rounds of conversation, through intent recognition, that is, through slot extraction, generation of question information, and conversation intent recognition, it can be determined whether the conversation intent is a fault problem. After multiple rounds of conversation, the robot engine can extract all slots in the target slot, perform conversation intent recognition on the multiple rounds of conversation information, and identify the conversation intent. The conversation intent can be a fault problem or a knowledge inquiry. In the case where the conversation intent is a fault problem, it indicates that fault feedback information needs to be generated. In the case where the conversation intent is a knowledge inquiry, knowledge recommendation content can be generated, the knowledge recommendation content can be pushed to the terminal device, and the knowledge recommendation content can be displayed on the user interface of the terminal device, for example, screen care tips, tips for extending the battery life of a mobile phone, etc.

[0145] In this embodiment of the present application, the intent of multiple rounds of dialogue can be not only fault feedback but also knowledge inquiries, increasing the diversity and richness of human-computer dialogue content. After multiple rounds of dialogue, the multi-round dialogue information is analyzed for dialogue intent. If the dialogue intent is identified as a fault, fault feedback information is generated and subsequent intelligent detection is performed. Compared to a unified solution that performs intelligent detection or knowledge recommendation after each round of dialogue, this method accurately identifies dialogue intent, reduces resource waste, and improves dialogue processing efficiency.

[0146] In one embodiment, please refer to Figure 7 The robot engine includes an intent recognition module, a slot extraction module, an intelligent question-and-answer module, and a task decision module, and may also include a knowledge recommendation module. The robot engine can use the slot extraction module to extract slots from user input information and obtain slot extraction results. Based on the slot extraction results, the intelligent question-and-answer module generates question information. The intent recognition module recognizes the intent of multiple rounds of dialogue information and obtains the dialogue intent. The task decision module assigns tasks based on the dialogue intent. For example, if the dialogue intent is a fault problem, fault feedback information is generated based on the round-by-round dialogue information and sent to the intelligent detection application so that the intelligent detection application can perform intelligent detection based on the fault feedback information. If the dialogue intent is a knowledge query, knowledge recommendation content is generated and pushed to the intelligent detection application for display.

[0147] S24. The server sends fault feedback information to the terminal device.

[0148] The server's robot engine sends fault feedback information to the intelligent detection application of the terminal device.

[0149] After receiving the fault feedback information, the terminal device can perform precise detection on the terminal device according to the fault feedback information and recommend a solution to the user in a targeted manner based on the detection results. For example, the process of detecting and recommending a solution based on the fault feedback information can include the following steps S25-S28.

[0150] S25. The terminal device determines a first fault scenario corresponding to the fault feedback information and a scenario fault tree corresponding to the first fault scenario.

[0151] In one embodiment, the intelligent detection application pre-sets multiple standardized fault scenarios. The intelligent detection application can determine the fault scenario corresponding to the fault feedback information from the multiple fault scenarios, that is, the fault scenario that matches the fault feedback information, and use the fault scenario as the first fault scenario.

[0152] In one embodiment, the intelligent detection application is further configured with a mapping relationship between fault scenarios and scenario fault trees. This mapping relationship includes a scenario fault tree corresponding to each of the multiple fault scenarios. The scenario fault tree corresponding to each fault scenario includes multiple fault nodes involved in each fault scenario, i.e., multiple factors that may cause the fault scenario. After determining the first fault scenario corresponding to the fault feedback information, the intelligent detection application may further determine the scenario fault tree corresponding to the first fault scenario based on the mapping relationship between the fault scenario and the scenario fault tree.

[0153] In addition, each fault node may also include at least one fault factor, that is, at least one factor that causes the fault node to fail. Multiple fault nodes can also be called first-level fault nodes, and the fault factor of each fault node can also be called second-level fault nodes. For example, the scenario fault tree for the two fault scenarios of "short video APP live broadcast freeze" and "instant messaging APP video call freeze" can be as follows: Figure 10 shown.

[0154] As an example, see Figure 7 The intelligent detection application includes a fault detection module, and the fault detection module can be used to determine the first fault scenario corresponding to the fault feedback information and the scenario fault tree corresponding to the first fault scenario.

[0155] As an example, see Figure 9The fault detection module includes a scenario conversion model and a diagnostic engine. The intelligent detection application can determine the first fault scenario corresponding to the fault feedback information through the scenario conversion model, and determine the scenario fault tree corresponding to the first fault scenario through the diagnostic engine. The scenario conversion model is used to determine the fault scenario corresponding to any fault feedback information from multiple fault feedback information, so as to convert different fault feedback information into corresponding standardized fault scenarios. The diagnostic engine can determine the fault scenario tree corresponding to any fault scenario from multiple fault scenarios, for example, based on the mapping relationship between the fault scenario and the scenario fault tree, to determine the fault scenario tree corresponding to any fault scenario.

[0156] S26. The terminal device performs fault detection on multiple fault nodes of the scenario fault tree corresponding to the first fault scenario respectively to obtain a fault detection result.

[0157] In one embodiment, a parsing rule matching the first faulty node among multiple parsing rules may be used to perform fault detection on the first faulty node to obtain a detection result for the first faulty node. The detection result of the first faulty node indicates whether the first faulty node has failed. The first faulty node is any one of multiple faulty nodes, and the fault detection result includes the detection results of the multiple faulty nodes.

[0158] That is, for different fault nodes in the scenario fault tree, multiple parsing rules can be pre-set, and different parsing rules are used to parse different fault nodes to detect whether the corresponding fault nodes are faulty. In this way, the accuracy of fault detection can be improved.

[0159] In one embodiment, performing fault detection on the first fault node using a parsing rule that matches the first fault node among multiple parsing rules, and obtaining a detection result may include: using a parsing rule that matches the first fault node among multiple parsing rules to parse the input data corresponding to the first fault node to obtain a detection result.

[0160] The input data corresponding to the first fault node refers to operational data related to the first fault node. The input data corresponding to the first fault node varies for different parsing rules. For example, the multiple parsing rules include at least two of the following parsing rules: fault rules, command rules, node rules, and code rules. For fault rules, the input data corresponding to the first fault node is fault dot data; for command rules, the input data corresponding to the first fault node is a database; for node rules, the input data corresponding to the first fault node is a system file or configuration file; and for code rules, the input data corresponding to the first fault node is logic execution data.

[0161] Please refer to Figure 12 , Figure 12This is a logical diagram of a fault scenario tree provided by an embodiment of the present application. Figure 12 As shown, a fault scenario can be constructed through a scene tree engine. Each fault scenario is a logical combination of one or more base scenes. Each node that causes a problem in the corresponding fault scenario is a base scene, and the base scene is a fault node. The scene tree engine can logically combine the input base scenes and output a fault scenario. In addition, different fault nodes can correspond to different input data and parsing rules, and the corresponding parsing rules can be used to parse their input data to achieve fault detection for the fault node. For example, for a fault node in a scenario fault tree, fault rules can be used to parse the relevant fault point data, or command rules can be used to parse the relevant database, or node rules can be used to parse the relevant system files or configuration files, or code rules can be used to parse the relevant logical operation data.

[0162] In one possible implementation, the scene tree engine can also configure a corresponding scene identifier, such as a scene identification (ID), for each constructed fault scenario. In addition, the scene tree engine can also traverse any fault scenario to see if it meets the corresponding rules (for example, whether each fault node in the scene fault tree of the fault scenario meets the corresponding rules). If so, it is determined that the fault scenario has occurred and an alarm is issued. For example, an alarm can be issued when the number of occurrences of the fault scenario exceeds a preset number. In addition, it is also possible to check whether the corresponding fault scenario has any abnormalities based on the alarm information.

[0163] Next, fault rules, command rules, node rules and code rules are introduced respectively.

[0164] Fault rules refer to rules for parsing fault management data. For example, fault rules may include data conditions and expected results, indicating that when the fault management data meets the data conditions, the corresponding fault node meets the expected result. The data conditions may include at least one of a time range, a threshold type, a threshold, etc., and the expected result may be a fault that occurs at the corresponding fault node. For example, please refer to Figure 13 , Figure 13 This is a schematic diagram of a scenario fault tree for detecting a jamming or unsmooth fault scenario provided by this application example. Figure 13 As shown in the figure, the scenario fault tree for the lag and unsmoothness fault scenario includes fault nodes such as "Application Unresponsiveness," "Slow Application Startup," "Memory Aging," and "Memory Leak." For the "Application Unresponsiveness" fault node, you can use fault rules to analyze its related fault tracking data. For example, if the fault tracking data contains a foreground application with more than a preset number of Class B trackings within a preset duration, then the application meets the criteria of Application Unresponsiveness.

[0165] Command rules refer to the rules for parsing the database. For example, a command rule may include a data reading statement, a data condition, and an expected result to indicate that the data reading statement is used to read data from the database. If the read data meets the data condition, the corresponding fault node meets the expected result. In addition, the command rule may also include a database path to indicate that data is read from the database corresponding to the database path. Among them, the data reading statement can be a Structured Query Language (SQL) database reading statement, the data condition can be a corresponding algorithm, etc., and the expected result can be a fault that occurs at the corresponding fault node. For example, please refer to Figure 13 For the fault scenario of lag and unsmoothness, the fault rule can be used to parse the database related to the fault node "slow application startup". For example, the value of CASENAME = "AAA" and the package name is "BBB" can be searched from the relevant database. If the value is greater than the first threshold, the application startup is slow.

[0166] Node rules refer to the rules for parsing system files or configuration files. For example, a node rule can include relevant fields and expected results in the file, indicating that if the relevant fields exist in the corresponding system file or configuration file, the corresponding fault node meets the expected result. The expected result can be a fault that occurs at the corresponding fault node. For example, please refer to Figure 13 For the fault scenario of lag and unsmooth operation, node rules can be used to parse the files related to "memory aging" of the faulty node. For example, the system node file can be read. If the value of a specific field in the system node file meets specific requirements, it indicates that the memory is aging.

[0167] Code rules refer to rules that are parsed by running a preset algorithm. For example, a code rule may include a preset algorithm (such as a custom algorithm), algorithm input parameters, and a result return, indicating that the result is returned after running the preset algorithm based on the algorithm input parameters. The returned result is used to indicate whether the corresponding fault node has failed. For example, the returned result can be (true) or (false), indicating that a fault has occurred, and (false) indicating that no fault has occurred. For example, please refer to Figure 13 For fault scenarios with lag and poor performance, code rules can be used to parse the logical execution data related to the "memory leak" of the fault node. For example, a custom algorithm can be run to match the memory growth limit points within a preset time from the fault point data, and obtain qualified leakage information from the matched memory growth limit points. If the number of qualified leakage information items is greater than or equal to the preset number, it indicates a memory leak.

[0168] In one embodiment, the correspondence between the faulty node and the parsing rule can be pre-configured so that when the first faulty node is detected, the parsing rule that matches the first faulty node can be determined based on the correspondence. In another embodiment, the faulty nodes can be divided into different node types in advance, and the correspondence between the node type and the parsing rule can be configured so that when the first faulty node is detected, the node type of the first faulty node can be determined first, and then the parsing rule that matches the first faulty node can be determined based on the correspondence. Of course, other methods can also be used to determine the parsing rule corresponding to the first faulty node, and the embodiments of the present application are not limited to this.

[0169] In addition, the first fault node may further include at least one fault factor that causes the first fault node to fail. The fault factor of the first fault node is the next-level fault node of the first fault node. For example, the first fault node may be referred to as a first-level fault node, and the fault factor may be referred to as a second-level fault node.

[0170] If the first fault node also includes at least one fault factor, the process of detecting the first fault node using a parsing rule that matches the first fault node among multiple parsing rules to obtain a detection result for the first fault node may further include: determining a parsing rule that matches each of the at least one fault factor from the multiple parsing rules, parsing each fault factor using the matching parsing rule, and obtaining a detection result corresponding to each fault factor, wherein the detection result corresponding to each fault factor indicates whether the corresponding fault factor has a fault. In this way, the detection result of each fault node includes the detection results of each fault factor of the fault node.

[0171] As an example, see Figure 9 The fault detection module includes a diagnosis engine, and the intelligent detection application can determine the scenario fault tree corresponding to the first fault scenario through the diagnosis engine, and perform fault detection on each fault node in the fault scenario tree.

[0172] S27. The terminal device determines a solution based on the fault detection result.

[0173] In one embodiment, the intelligent detection application can determine a solution based on the fault detection results and service data. Service data can include one or more of service tickets, maintenance records, and a knowledge base. For example, the intelligent detection application can determine whether the fault detection result is a software or hardware issue based on the service data, and then determine a solution based on the fault detection result and the problem type. This can further improve the accuracy of the solution determination.

[0174] In one embodiment, the solution may include one or more of: handling suggestions, knowledge recommendations, guidance on branch maintenance methods, and fault repair execution methods. Handling suggestions include repair suggestions or operational recommendations. Knowledge recommendations include explanations related to the fault, which can be accessed through the knowledge base. Guidance on branch maintenance methods may include information about branch maintenance processes, such as mail-in repair methods or scheduled repair methods. Fault repair methods may include automatic repair methods or manual repair methods, which trigger the device to automatically repair the fault.

[0175] As an example, see Figure 7 ,The intelligent detection application includes a solution recommendation module, ,through which solutions can be determined based on the fault detection ,results.

[0176] S28. The terminal device displays a second interface, which includes relevant information about the solution.

[0177] Among them, the relevant information of the solution is used to indicate the solution, which may include a description of the fault, and may also include one or more of processing suggestions, viewing suggestion controls, maintenance controls, and optimization controls. The viewing suggestion control is used to trigger relevant knowledge about the equipment fault, such as triggering the display of relevant knowledge about the fault corresponding to the fault feedback information or guiding information for viewing relevant knowledge, and the guiding information is used to guide the user to view the relevant knowledge. The maintenance control (such as the "Guide Maintenance" control or the "I Want Repair" control, etc.) is used to trigger the guidance information of the branch maintenance process to guide the user to send in for repair or make an appointment for repair. The optimization control (such as the "One-click Optimization" control or the "Optimize Now" control) is used to trigger the device to automatically modify the fault, such as repairing the fault corresponding to the fault feedback information.

[0178] As an example, the solution-related information includes one or more of a view suggestion control, a repair control, and an optimization control. If the solution-related information includes the view suggestion control, in response to a triggering operation on the view suggestion control, relevant knowledge about the fault corresponding to the fault feedback information or guidance information for viewing relevant knowledge is displayed. If the solution-related information includes a repair control, in response to a triggering operation on the repair control, guidance information on the branch repair process is displayed to guide the user to send in a repair or schedule a repair. If the solution-related information includes an optimization control, in response to a triggering operation on the optimization control, the fault corresponding to the fault feedback information is repaired.

[0179] For example, Figure 6 The solution information shown in Figure (a) includes fault description and handling suggestions. Figure 6The solution-related information shown in Figure (b) includes fault description, handling suggestions, and a "View Suggestions" control. Users can click the "View Suggestions" control to view relevant knowledge about the current device fault in the knowledge base. Figure 6 The solution information shown in Figure (c) includes fault description, handling suggestions and the "I want repair" control. Users can click the "I want repair" control to send in the repair or schedule a repair. Figure 6 The solution information shown in Figure (d) includes a description of the fault, handling suggestions, and a "one-click optimization" control. Users can click the "one-click optimization" control to trigger the device to automatically repair itself.

[0180] The information processing method provided in the embodiment of the present application relies on large model technology based on self-detection related functions, and realizes accurate classification of user faults based on multiple rounds of dialogues for slot filling constructed by online customer service. It can accurately identify user faults, encountered fault scenarios and specific applications. In addition, faults are detected based on the construction of a scenario fault tree, and accurate solutions can be pushed according to the detection results.

[0181] Next, the terminal device involved in the embodiment of the present application is described.

[0182] Figure 14 This is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application. The terminal device can be the above Figure 7 See the end side of the Figure 14 The terminal device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. Among them, the sensor module 180 can include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0183] It should be understood that the structures illustrated in the embodiments of the present application do not constitute a specific limitation on the terminal device 100. In other embodiments of the present application, the terminal device 100 may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0184] The processor 110 may include one or more processing units, for example, an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). The different processing units may be independent devices or integrated into one or more processors.

[0185] The controller may be the nerve center and command center of the terminal device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0186] Processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in processor 110 is a cache memory. This memory can store instructions or data that have just been used or are being recycled by processor 110. If processor 110 needs to use the same instruction or data again, it can directly access the memory. This avoids duplicate accesses, reduces processor 110 latency, and thus improves system efficiency.

[0187] In some embodiments, the processor 110 may include one or more interfaces, such as an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0188] The wireless communication function of the terminal device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

[0189] Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in terminal device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In other embodiments, the antennas can be used in conjunction with a tuning switch.

[0190] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G applied to the terminal device 100. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, and filter, amplify, and process the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the same device as at least some of the modules of the processor 110.

[0191] The modem processor may include a modulator and a demodulator. The modulator is used to modulate the low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After being processed by the baseband processor, the low-frequency baseband signal is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to the speaker 170A, the receiver 170B, etc.) or displays an image or video through the display screen 194. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 110 and be set in the same device as the mobile communication module 150 or other functional modules.

[0192] The wireless communication module 160 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc. applied to the terminal device 100. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, frequency modulate it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0193] In some embodiments, antenna 1 of terminal device 100 is coupled to mobile communication module 150, and antenna 2 is coupled to wireless communication module 160, so that terminal device 100 can communicate with a network and other devices via wireless communication technology. Wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology. GNSS may include the global positioning system (GPS), the global navigation satellite system (GLONASS), the Beidou navigation satellite system (BDS), the quasi-zenith satellite system (QZSS) and / or the satellite based augmentation system (SBAS).

[0194] The terminal device 100 implements display functions through a GPU, display screen 194, and an application processor. The GPU is a microprocessor for image processing that connects the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or modify display information.

[0195] Display screen 194 is used to display images, videos, etc. Display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a MiniLED, a MicroLED, a Micro-oLed, or a quantum dot light-emitting diode (QLED). In some embodiments, terminal device 100 may include one or N display screens 194, where N is an integer greater than one.

[0196] The terminal device 100 can realize the shooting function through the ISP, camera 193, video codec, GPU, display screen 194 and application processor.

[0197] The ISP processes data fed back by camera 193. For example, when taking a photo, the shutter is opened, and light is transmitted through the lens to the camera's photosensitive element. The light signal is converted into an electrical signal, which is then passed to the ISP for processing and transformed into a visible image. The ISP can also perform algorithmic optimization on image noise, brightness, and skin tone. It can also optimize parameters such as exposure and color temperature of the captured scene. In some embodiments, the ISP can be located within camera 193.

[0198] The camera 193 is used to capture still images or videos. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, and then passes the electrical signal to the ISP for conversion into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV or other format. In some embodiments, the terminal device 100 may include 1 or N cameras 193, where N is an integer greater than 1.

[0199] The digital signal processor is used to process digital signals. In addition to processing digital image signals, it can also process other digital signals. For example, when the terminal device 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy.

[0200] Video codecs are used to compress or decompress digital video. Terminal device 100 may support one or more video codecs. This allows terminal device 100 to play or record videos in various encoding formats, such as Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, and MPEG4.

[0201] The NPU is a neural network (NN) computing processor. Drawing on the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it rapidly processes input information and can continuously self-learn. The NPU enables intelligent cognitive applications in the terminal device 100, such as image recognition, face recognition, speech recognition, and text comprehension.

[0202] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the terminal device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement data storage functions. For example, files such as music and videos can be stored on the external memory card.

[0203] The internal memory 121 can be used to store computer executable program codes, which include instructions. The processor 110 executes various functional applications and data processing of the terminal device 100 by running the instructions stored in the internal memory 121. The internal memory 121 may include a program storage area and a data storage area. The program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created by the terminal device 100 during use (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0204] The terminal device 100 can implement audio functions, such as music playback, recording, etc., through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone jack 170D and the application processor.

[0205] Pressure sensor 180A is used to sense pressure signals and convert them into electrical signals. In some embodiments, pressure sensor 180A can be located on display screen 194. There are many types of pressure sensors 180A, such as resistive, inductive, and capacitive. A capacitive pressure sensor can include at least two parallel plates made of conductive material. When force is applied to pressure sensor 180A, the capacitance between the electrodes changes. Terminal device 100 determines the intensity of the pressure based on this change in capacitance. When a touch operation is applied to display screen 194, terminal device 100 detects the touch intensity based on pressure sensor 180A. Terminal device 100 can also calculate the touch location based on the detection signal from pressure sensor 180A. In some embodiments, touch operations applied to the same touch location but with different touch intensities can correspond to different operation instructions. For example, when a touch operation with an intensity less than a pressure threshold is applied to a short message application icon, a command to view short messages is executed. When a touch operation with an intensity greater than or equal to the pressure threshold is applied to a short message application icon, a command to create a new short message is executed.

[0206] The touch sensor 180K is also called a "touch panel." The touch sensor 180K can be set on the display screen 194. The touch sensor 180K and the display screen 194 form a touch screen, also called a "touch screen." The touch sensor 180K is used to detect touch operations acting on or near it. The touch sensor 180K can transmit the detected touch operation to the application processor to determine the type of touch event. Visual output related to the touch operation can be provided through the display screen 194. In other embodiments, the touch sensor 180K can also be set on the surface of the terminal device 100, at a different location from the display screen 194.

[0207] Figure 15 This is a schematic diagram of the structure of a server provided in an embodiment of the present application. The server may be the above-mentioned Figure 7 Servers on the Zhongyun side. Figure 15 The server includes at least one processor 201 , a communication bus 202 , a memory 203 and at least one communication interface 204 .

[0208] The processor 201 may be a microprocessor (including a central processing unit (CPU) etc.), an application-specific integrated circuit (ASIC), or may be one or more integrated circuits for controlling the execution of the program of the present application.

[0209] The communication bus 202 may include a pathway for transmitting information between the aforementioned components.

[0210] The memory 203 may be a read-only memory (ROM), a random access memory (RAM), an electrically erasable programmable read-only memory (EEPROM), an optical disc (including a compact disc read-only memory (CD-ROM), a compact disc, a laser disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 203 may exist independently and be connected to the processor 201 via the communication bus 202. The memory 203 may also be integrated with the processor 201.

[0211] The communication interface 204 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0212] In a specific implementation, as an embodiment, the processor 201 may include one or more CPUs, such as Figure 15 CPU0 and CPU1 are shown in the figure.

[0213] In a specific implementation, as an embodiment, the server may include multiple processors, such as Figure 15 1 and 2. Each of these processors may be a single-core processor or a multi-core processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0214] The server can be a general-purpose server or a dedicated server. In a specific implementation, the server can be a desktop computer, a portable computer, a network server, a palmtop computer, a mobile phone, a tablet computer, a wireless server, a communication device or an embedded device. The embodiment of the present application does not limit the type of server.

[0215] The memory 203 is used to store the program code 210 for executing the solution of the present application, and the processor 201 is used to execute the program code 210 stored in the memory 203. The server can implement the server execution method described in the following embodiments through the processor 201 and the program code 210 in the memory 203.

[0216] An embodiment of the present application also provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, it enables the computer to execute the method executed by the terminal device and / or server in the above embodiment.

[0217] An embodiment of the present application also provides a computer program product containing instructions, which, when executed on a computer, enables the computer to execute the method executed by the terminal device and / or server in the above embodiment.

[0218] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (such as a coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0219] The above are optional embodiments provided for this application and are not intended to limit this application. Any modifications, equivalent replacements, improvements, etc. made within the technical scope disclosed in this application should be included in the scope of protection of this application.

Claims

1. An information processing method, characterized in that: Applied to a terminal device, the method includes: Displaying a first interface; the first interface includes a problem feedback window, which is used to provide an interactive entry for the user and the server to conduct multiple rounds of dialogue, so that the server generates fault feedback information based on the multi-round dialogue information, and the fault feedback information is used to indicate the fault scenario; receiving the fault feedback information sent by the server; Determine a first fault scenario corresponding to the fault feedback information and a scenario fault tree corresponding to the first fault scenario, wherein the scenario fault tree includes multiple fault nodes involved in the first fault scenario; Performing fault detection on each of the multiple faulty nodes, and determining a solution based on the fault detection results; A second interface is displayed, where the second interface includes relevant information about the solution.

2. The method according to claim 1, wherein Before receiving the fault feedback information sent by the server, the method further includes: detecting first user input information in the question feedback window, and sending the first user input information to the server; receiving and displaying in the problem feedback window a question message sent by the server, wherein the question message is generated by the server after performing slot extraction on the first user input information, wherein the target slot extracted from the slot extraction includes at least a fault type; Detecting second user input information in the question feedback window, sending the second user input information to the server until the fault feedback information sent by the server is received, the second user input information is the user's reply information based on the question information, and the multi-round dialogue information includes at least the first user input information, the second user input information and the question information.

3. The method according to claim 2, wherein The target slot further includes at least one of an application identifier of the faulty application, a fault occurrence time, a fault occurrence frequency, and a problem summary.

4. The method according to any one of claims 1 to 3, characterized in that: The fault feedback information includes fault information of a fault occurring in the first application.

5. The method according to any one of claims 1 to 4, characterized in that: The determining the first fault scenario corresponding to the fault feedback information and the scenario fault tree corresponding to the first fault scenario includes: Determining a fault scenario corresponding to the fault feedback information from multiple fault scenarios, the fault scenario corresponding to the fault feedback information being the first fault scenario; According to the mapping relationship between the fault scenario and the scenario fault tree, a scenario fault tree corresponding to the first fault scenario is determined.

6. The method according to any one of claims 1 to 5, characterized in that: The performing fault detection on the multiple fault nodes respectively to obtain fault detection results includes: performing fault detection on the first fault node using a parsing rule that matches the first fault node among the plurality of parsing rules, and obtaining a detection result of the first fault node, where the first fault node is any one of the plurality of fault nodes, and the detection result is used to indicate whether the first fault node has a fault; Among them, the multiple parsing rules include at least two of the following parsing rules: fault rules, command rules, node rules and code rules; the fault rules refer to rules for parsing fault management data, the command rules refer to rules for parsing databases, the node rules refer to rules for parsing system files or configuration files, and the code rules refer to rules for parsing by running preset algorithms.

7. The method according to claim 6, wherein The first faulty node includes at least one fault factor that causes the first faulty node to fail. The detecting the first faulty node using an analysis rule that matches the first faulty node among the multiple analysis rules to obtain a detection result of the first faulty node includes: Determine an analysis rule that matches each fault factor in the at least one fault factor from the multiple analysis rules, use the matching analysis rule to analyze each fault factor, and obtain a detection result corresponding to each fault factor. The detection result corresponding to each fault factor is used to indicate whether a fault occurs in the corresponding fault factor.

8. The method according to any one of claims 1 to 7, wherein: The solution includes at least one of processing suggestions, knowledge recommendation content, guiding network maintenance methods and executing fault repair methods.

9. The method according to any one of claims 1 to 8, wherein: The solution-related information includes viewing one or more of a suggestion control, a repair control, and an optimization control; In a case where the solution-related information includes the view suggestion control, in response to a triggering operation on the view suggestion control, displaying relevant knowledge of the fault corresponding to the fault feedback information or guidance information of the relevant knowledge; In a case where the relevant information of the solution includes the maintenance control, in response to a triggering operation of the maintenance control, guidance information of the branch maintenance process is displayed to guide the user to send in the product for repair or make an appointment for repair; In a case where the relevant information of the solution includes the optimization control, in response to a triggering operation on the optimization control, the fault corresponding to the fault feedback information is repaired.

10. An information processing method, characterized in that: The method is applied to a server and includes: generating fault feedback information based on multi-round dialogue information in a problem feedback window of a terminal device; the problem feedback window is used to provide an interactive entry for the user and the server to conduct multi-round dialogues, and the fault feedback information is used to indicate a fault scenario; Sending the fault feedback information to the terminal device.

11. The method according to claim 10, wherein Generating fault feedback information according to the multi-round dialogue information in the problem feedback window of the terminal device includes: Receiving first user input information in the question feedback window sent by the terminal device; Performing slot extraction on the first user input information to obtain a slot extraction result, wherein the target slot of the slot extraction includes at least a fault type; If the slot extraction result indicates that slot information of at least some of the target slots has not been extracted, generating question information according to the slot extraction result, the question information being used to instruct a user to provide the slot information of at least some of the target slots; Sending the question information to the terminal device; Continue to receive the second user input information in the problem feedback window sent by the terminal device until the slot information of all slots in the target slot is extracted based on the multi-round dialogue information with the user, and generate the fault feedback information based on the multi-round dialogue information; wherein, the second user input information indicates the user's reply information based on the question information, and the multi-round dialogue information includes at least the first user input information, the second user input information and the question information.

12. An information processing method, characterized in that: The method is applied to an information processing system, which includes a terminal device and a server, and includes: The terminal device displays a first interface; the first interface includes a question feedback window, and the question feedback window is used to provide an interactive entrance for the user and the server to conduct multiple rounds of dialogue; The server generates fault feedback information based on the multi-round dialogue information in the problem feedback window of the terminal device, where the fault feedback information is used to indicate the fault scenario; The server sends the fault feedback information to the terminal device; The terminal device determines a first fault scenario corresponding to the fault feedback information and a scenario fault tree corresponding to the first fault scenario, where the scenario fault tree includes multiple fault nodes involved in the first fault scenario; performs fault detection on each of the multiple fault nodes, and determines a solution based on the fault detection results; The terminal device displays a second interface, where the second interface includes relevant information about the solution.

13. The method according to claim 12, wherein: The method further comprises: The terminal device detects first user input information in the question feedback window, and sends the first user input information to the server; The server performs slot extraction on the first user input information to obtain a slot extraction result, where the target slot of the slot extraction includes at least a fault type; When the slot extraction result indicates that slot information of at least some of the target slots has not been extracted, the server generates question information according to the slot extraction result, and sends the question information to the terminal device, wherein the question information is used to instruct the user to provide the slot information of at least some of the target slots; The terminal device displays the question information in the problem feedback window, detects second user input information in the problem feedback window, and sends the second user input information to the server until the server extracts the slot information of all slots in the target slot based on multi-round dialogue information with the user, and generates the fault feedback information based on the multi-round dialogue information; wherein, the second user input information indicates the user's reply information based on the question information, and the multi-round dialogue information includes at least the first user input information, the second user input information and the question information.

14. A terminal device, characterized in that: The terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method according to any one of claims 1 to 9 when executed by the processor.

15. A server, characterized in that: The server includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method according to claim 10 or 11 when executed by the processor.

16. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 9, or the method according to claim 10 or 11.

17. A computer program product comprising instructions, characterized in that When the method is run on a computer, the computer is enabled to execute the method according to any one of claims 1 to 9, or the method according to claim 10 or 11.

Images